2021

Ordered physical human activity recognition based on ordinal classification

Human activity recognition (HAR) is a critical process for applications that focus on the classification of human physical activities such as jogging, walking, downstairs, and upstairs. Ordinal classification (OC) is a special type of supervised multi-class classification in which an inherent ordering among the classes exists, such as low, medium, and high. This study combines these two concepts and introduces an approach to “human activity recognition based on ordinal classification” (HAROC). In the proposed approach, ordinal classification is applied to human activity recognition where the physical activities can be ordered by using their signals’ band power values. This is the first study that investigates the performance of the HAROC approach by combining the ordinal classification with eight different base learners. Besides, this study is also original in that it examines the effects of the demographic characteristics of the participants (i.e., sex, age, weight, and height) on the classification performance. The experiments carried out on a real-world dataset show that the proposed HAROC approach is an effective method for human activity recognition tasks.

PDF

___

[1] Tolba A, Al-Makhadmeh Z. Wearable sensor-based fuzzy decision-making model for improving the prediction of human activities in rehabilitation. Measurement 2020; 166: 1-11. doi: 10.1016/j.measurement.2020.108254
[2] Wang Y, Cang S, Yu H. A survey on wearable sensor modality centred human activity recognition in health care. Expert Systems with Applications 2019; 137: 167-190. doi: 10.1016/j.eswa.2019.04.057
[3] Mukherjee A, Misra S, Mangrulkar P, Rajarajan M, Rahulamathavan Y. SmartARM: a smartphone-based group activity recognition and monitoring scheme for military applications. In: IEEE 2017 ANTS International Conference on Advanced Networks and Telecommunications Systems; Bhubaneswar, India; 2017. pp. 1-6. doi: 10.1109/ants.2017.8384149
[4] Supriyatna TB, Nasution SM, Nugraheni RA. Human activity recognition using support vector machine for automatic security system. Journal of Physics 2019; 1192: pp. 1-10. doi: 10.1088/1742-6596/1192/1/012017
[5] Frank E, Mark H. A simple approach to ordinal classification. In: European Conference on Machine Learning; Freiburg, Germany; 2001. pp. 145-156. doi: 10.1007/3-540-44795-4_13
[6] Nguyen B, Morell C, Baets BD. Distance metric learning for ordinal classification based on triplet constraints. Knowledge-Based Systems 2018; 142: 17-28. doi: 10.1016/j.knosys.2017.11.022
[7] Campoy-Muñoz P, Gutiérrez PA, Hervás-Martínez C. Addressing remitting behavior using an ordinal classification approach. Expert Systems with Applications 2014; 41 (10): 4752-4761. doi: 10.1016/j.eswa.2014.01.036
[8] Chen Y, Shen C. Performance analysis of smartphone-sensor behavior for human activity recognition. IEEE Access 2017; 5: 3095–3110. doi: 10.1109/access.2017.2676168
[9] Chen Z, Zhu Q, Soh YC, Zhang L. Robust human activity recognition using smartphone sensors via CT-PCA and online SVM. IEEE Transactions on Industrial Informatics 2017; 13 (6): 3070-3080. doi: 10.1109/tii.2017.2712746
[10] Shoaib M, Bosch S, Durmaz Incel O, Scholten H, Havinga PJM. Fusion of smartphone motion sensors for physical activity recognition. Sensors 2014; 14 (6): 10146-10176. doi: 10.3390/s140610146
[11] Saylam B, Shoaib M, Durmaz Incel O. Exploring the parameter space of human activity recognition with mobile devices. Turkish Journal of Electrical Engineering & Computer Sciences 2020; 28 (6). doi: 10.3906/elk-1910-139
[12] Kerdjidj O, Ramzan N, Ghanem K, Amira A, Chouireb F. Fall detection and human activity classification using wearable sensors and compressed sensing. Journal of Ambient Intelligence and Humanized Computing 2020; 11: 349-361. doi: 10.1007/s12652-019-01214-4
[13] Gjoreski M, Janko V, Slapnicar G, Mlakar M, Rescic N et al. Classical and deep learning methods for recognizing human activities and modes of transportation with smartphone sensors. Information Fusion 2020; 62: 47–62. doi: 10.1016/j.inffus.2020.04.004
[14] Zalluhoglu C, Ikizler-Cinbis N. Collective sports: a multi-task dataset for collective activity recognition. Image and Vision Computing 2020; 94: 1-11. doi: 10.1016/j.imavis.2020.103870
[15] Janidarmian M, Fekr AR, Radecka K, Zilic Z. A comprehensive analysis on wearable acceleration sensors in human activity recognition. Sensors 2017; 17 (3): 1-26. doi: 10.3390/s17030529
[16] San-Segundo R, Blunck H, Moreno-Pimentel J, Stisen A, Gil-Martín M. Robust human activity recognition using smartwatches and smartphones. Engineering Applications of Artificial Intelligence 2018; 72: 190-202. doi: 10.1016/j.engappai.2018.04.002
[17] Guijo-Rubio D, Gutiérrez PA, Casanova-Mateo C, Sanz-Justo J, Salcedo-Sanz S et al. Prediction of lowvisibility events due to fog using ordinal classification. Atmospheric Research 2018; 214: 64-73. doi: 10.1016/j.atmosres.2018.07.017
[18] Manthoulis G, Doumpos M, Zopounidis C, Galariotis E. An ordinal classification framework for bank failure prediction: methodology and empirical evidence for US banks. European Journal of Operational Research 2020; 282 (2): 786-801. doi: 10.1016/j.ejor.2019.09.040
[19] Rahiche A, Hedjam R, Al-maadeed S, Cheriet M. Historical documents dating using multispectral imaging and ordinal classification. Journal of Cultural Heritage, in press. doi: 10.1016/j.culher.2020.01.012
[20] Gutiérrez PA, Pérez-Ortiz M, Sánchez-Monedero J, Fernández-Navarro F, Hervás-Martínez C. Ordinal regression methods: survey and experimental study. IEEE Transactions on Knowledge and Data Engineering 2016; 28 (1): 127-146. doi: 10.1109/TKDE.2015.2457911
[21] Sousa R, Yevseyeva I, Costa JFP, Cardoso JS. Multicriteria models for learning ordinal data: a literature review. In: Yang XS (editor). Artificial Intelligence, Evolutionary Computing and Metaheuristics. Berlin, Germany: Springer, 2013, pp.109-138.
[22] Halsey LG, Watkins DAR, Duggan BM. The energy expenditure of stair climbing one step and two steps at a time: estimations from measures of heart rate. Plos One 2012; 7 (12): 1-6. doi:10.1371/journal.pone.0051213
[23] Qu Y, Gao Z, Xiao Y, Li X. Modeling the pedestrian’s movement and simulating evacuation dynamics on stairs. Safety Science 2014; 70: 189-201. doi: 10.1016/j.ssci.2014.05.016
[24] Hackett S, Cai Y, Siegel M. Activity recognition from sensor fusion on fireman’s helmet. In: 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI); Huaqiao, China; 2019. pp. 1-6. doi: 10.1109/CISP-BMEI48845.2019.8966005
[25] Wang L, Qian Q, Zhang Q, Wang J, Cheng W et al. Classification model on big data in medical diagnosis based on semi-supervised learning. The Computer Journal 2020; bxaa006: 1-15. doi:10.1093/comjnl/bxaa006
[26] Muñoz-Almaraz FJ, Zamora-Martínez F, Botella-Rocamora P, Pardo J. Supervised filters for EEG signal in naturally occurring epilepsy forecasting. Plos One 2017; 12: 1-17. doi:10.1371/journal.pone.0178808
[27] Xiao P, Qu W, Qi H, Li Z. Detecting DDoS attacks against data center with correlation analysis. Computer Communications 2015; 67: 66-74. doi:10.1016/j.comcom.2015.06.012
[28] Witten IH, Frank E, Hall MA, Pal CJ. Data Mining: Practical Machine Learning Tools and Techniques. 4th ed. Cambridge, MA, USA: Morgan Kaufmann, 2016.
[29] Jiang D, Ma P, Su X, Tiantian W. Distance metric based divergent change bad smell detection and refactoring scheme analysis. International Journal of Innovative Computing, Information and Control 2014; 10 (4): 1519-1531.
[30] Shmulevich I, Dougherty D. Genomic Signal Processing. Princeton, NJ, USA: Princeton University Press, 2007.
[31] Mercado P, Lukashevich H. Applying constrained clustering for active exploration of music collections. In: Proceedings of the 1st Workshop on Music Recommendation and Discovery (WOMRAD); Barcelona, Spain; 2010. pp. 39-46.
[32] Malekzadeh M, Clegg RG, Cavallaro A, Haddadi H. Protecting sensory data against sensitive inferences. In: Proceedings of the 1st Workshop on Privacy by Design in Distributed Systems; Porto, Portugal; 2018. pp. 1-6. doi: 10.1145/3195258.3195260
[33] Ferrari A, Mobilio M, Micucci D, Napoletano P. On the homogenization of heterogeneous inertial-based databases for human activity recognition. In: 2019 IEEE World Congress on Services (SERVICES); Milan, Italy; 2019. pp. 295-300. doi: 10.1109/SERVICES.2019.00084.
[34] Kuncan F, Kaya Y, Kuncan M. A novel approach for activity recognition with down-sampling 1D local binary pattern features. Advances in Electrical and Computer Engineering 2019; 19: 35-44. doi:10.4316/AECE.2019.01005
[35] Gil-Martín M, Sánchez-Hernández M, San-Segundo R. Human activity recognition based on deep learning techniques. Proceedings 2020; 42 (1): 1-6. doi: 10.3390/ecsa-6-06539
[36] Batool M, Jalal A, Kim K. Sensors technologies for human activity analysis based on SVM optimized by PSO algorithm. In: 2019 International Conference on Applied and Engineering Mathematics (ICAEM); Taxila, Pakistan; 2019. pp. 145-150. doi: 10.1109/ICAEM.2019.8853770
[37] Jalal A, Batool M, Kim K. Stochastic recognition of physical activity and healthcare using tri-axial inertial wearable sensors. Applied Sciences 2020; 10 (20): 1-20. doi: 10.3390/app10207122
[38] Boutet A, Frindel C, Gambs S, Jourdan T, Ngueveu RC. DYSAN: dynamically sanitizing motion sensor data against sensitive inferences through adversarial networks. In: 34th Conference on Neural Information Processing Systems (NeurIPS 2020); Vancouver, Canada; 2020. pp. 1-10.
[39] Fermanian A. Embedding and learning with signatures. Computational Statistics and Data Analysis 2021; 157: 1-23. doi: 10.1016/j.csda.2020.107148
[40] Ferrari A, Micucci D, Mobilio M, Napoletano P. On the personalization of classification models for human activity recognition. IEEE Access 2020; 8: 32066-32079. doi: 10.1109/ACCESS.2020.2973425
[41] Saeed A, Ozcelebi T, Lukkien J. Multi-task self-supervised learning for human activity detection. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 2019; 3 (2): 1-30. doi: 10.1145/3328932
[42] Malekzadeh M, Clegg RG, Cavallaro A, Haddadi H. Protecting sensory data against sensitive inferences. In: Proceedings of the 1st Workshop on Privacy by Design in Distributed Systems; Porto, Portugal; 2018. pp. 1-6. doi: 10.1145/3195258.3195260
[43] Gamble JA, Huang J. Convolutional neural network for human activity recognition and identification. In: IEEE International Systems Conference (SysCon); Dublin, Ireland; 2018. pp. 1-7. doi: 10.1109/SysCon47679.2020.9275924